© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57905
    Prev
    Next
    INDEX
    Explanations

    references to specific universities and their engineering programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kansas
    -0.11
    Kansas
    -0.11
    .ibm
    -0.09
     Egyptian
    -0.09
     Egypt
    -0.08
     Cairo
    -0.08
    Egypt
    -0.08
    gypt
    -0.08
     Benghazi
    -0.07
     Django
    -0.07
    POSITIVE LOGITS
     Houston
    0.13
    Houston
    0.12
     Trafford
    0.10
     Rice
    0.09
     Mosul
    0.09
     Brisbane
    0.09
     Norwich
    0.08
     Manchester
    0.08
     rice
    0.07
     Baltimore
    0.07
    Activations Density 0.064%

    No Known Activations